© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19560
    Prev
    Next
    INDEX
    Explanations

    COR words and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -3.53
     "
    -3.17
        
    -3.00
    ET
    -2.77
    AN
    -2.70
    of
    -2.58
    この日
    -2.55
    ES
    -2.44
    U
    -2.41
    ED
    -2.34
    POSITIVE LOGITS
    ר
    3.11
    ه
    2.98
    胧
    2.78
    齶
    2.72
     начале
    2.61
    namentales
    2.55
     zví
    2.47
     Públicas
    2.45
    ">“
    2.45
     tijdens
    2.44
    Activations Density 0.002%

    No Known Activations